Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 994 235 226 556 177 662   2 174 978 995 474 934 930 122   9 254 571 757 856 343
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 343   2 122 757 254 556 174 930   9 934  NA 235 474 571 177 978 856 226 995 662  NA  NA 994
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 3 5 1 2 5 4 1 1 5
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "o" "w" "d" "p" "j" "Y" "L" "A" "D" "R"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  1  9 10 12 13
which( manyNumbersWithNA > 900 )
[1]  8 10 16 19 23
which( is.na( manyNumbersWithNA ) )
[1] 11 21 22

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 994 978 995 934 930
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 994 978 995 934 930
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 994 978 995 934 930

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "Y" "L" "A" "D" "R"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "o" "w" "d" "p" "j"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE
[18] FALSE FALSE  TRUE
which( manyNumbers %in% 300:600 )
[1]  4 11 17 20
sum( manyNumbers %in% 300:600 )
[1] 4

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "small" "small" "small" "large" "small" "large" "small" "large" "small" "large" NA      "small" "small"
[14] "large" "small" "large" "large" "small" "large" "large" NA      NA      "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "small"   "small"   "small"   "large"   "small"   "large"   "small"   "large"   "small"   "large"  
[11] "UNKNOWN" "small"   "small"   "large"   "small"   "large"   "large"   "small"   "large"   "large"  
[21] "UNKNOWN" "UNKNOWN" "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]   0   0   0 757   0 556   0 930   0 934  NA   0   0 571   0 978 856   0 995 662  NA  NA 994

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 3 5 2 4
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  3  5  2  4
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 19
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 995
which.min( manyNumbersWithNA )
[1] 2
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 2
range( manyNumbersWithNA, na.rm = TRUE )
[1]   2 995

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 343   2 122 757 254 556 174 930   9 934  NA 235 474 571 177 978 856 226 995 662  NA  NA 994
sort( manyNumbersWithNA )
 [1]   2   9 122 174 177 226 235 254 343 474 556 571 662 757 856 930 934 978 994 995
sort( manyNumbersWithNA, na.last = TRUE )
 [1]   2   9 122 174 177 226 235 254 343 474 556 571 662 757 856 930 934 978 994 995  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 995 994 978 934 930 856 757 662 571 556 474 343 254 235 226 177 174 122   9   2  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 343   2 122 757 254
order( manyNumbersWithNA[1:5] )
[1] 2 3 5 1 4
rank( manyNumbersWithNA[1:5] )
[1] 4 1 2 5 3
sort( mixedLetters )
 [1] "A" "d" "D" "j" "L" "o" "p" "R" "w" "Y"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1] 3.0 9.0 5.5 2.0 5.5 9.0 1.0 5.5 9.0 5.5
rank( manyDuplicates, ties.method = "min" )
 [1] 3 8 4 2 4 8 1 4 8 4
rank( manyDuplicates, ties.method = "random" )
 [1]  3  8  7  2  5 10  1  4  9  6

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -0.3171865  1.5420147  1.5895282 -1.6170689
[10] -1.2662685  1.6010349  0.2788430  1.2945722  0.5673192 -0.1103653
round( v, 0 )
 [1] -1  0  0  0  1  0  2  2 -2 -1  2  0  1  1  0
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.3  1.5  1.6 -1.6 -1.3  1.6  0.3  1.3  0.6 -0.1
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.32  1.54  1.59 -1.62 -1.27  1.60  0.28  1.29  0.57 -0.11
floor( v )
 [1] -1 -1  0  0  1 -1  1  1 -2 -2  1  0  1  0 -1
ceiling( v )
 [1] -1  0  0  1  1  0  2  2 -1 -1  2  1  2  1  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC